Pose Estimation of Kinematic Chain Instances via Object Coordinate Regression

Frank Michel, Alexander Krull, Eric Brachmann, Michael Ying Yang, Stefan Gumhold and Carsten Rother

Abstract

In this paper, we address the problem of one shot pose estimation of articulated objects from an RGB-D image. In particular, we consider object instances with the topology of a kinematic chain, i.e. assemblies of rigid parts connected by prismatic or revolute joints. This object type occurs often in daily live, for instance in the form of furniture or electronic devices. Instead of treating each object part separately, we are using the relationship between parts of the kinematic chain and propose a new minimal pose sampling approach. This enables us to create a pose hypothesis for a kinematic chain consisting of K parts by sampling K 3D-3D point correspondences. To asses the quality of our method, we gathered a large dataset containing four objects and 7000+ annotated RGB-D frames. On this dataset we achieve considerably better results than a modified state-of-the-art pose estimation system for rigid objects.

Session

Tracking and Pose Estimation

Files

Extended Abstract (PDF, 3M)
Paper (PDF, 9M)
Supplemental Materials (ZIP, 111K)

DOI

10.5244/C.29.181
https://dx.doi.org/10.5244/C.29.181

Citation

Bibtex

@inproceedings{BMVC2015_181,
	title={Pose Estimation of Kinematic Chain Instances via Object Coordinate Regression},
	author={Frank Michel and Alexander Krull and Eric Brachmann and Michael Ying Yang and Stefan Gumhold and Carsten Rother},
	year={2015},
	month={September},
	pages={181.1-181.11},
	articleno={181},
	numpages={11},
	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
	publisher={BMVA Press},
	editor={Xianghua Xie, Mark W. Jones, and Gary K. L. Tam},
	doi={10.5244/C.29.181},
	isbn={1-901725-53-7},
	url={https://dx.doi.org/10.5244/C.29.181}
}